© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7352
    Prev
    Next
    INDEX
    Explanations

    STATEMENT or following words

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on non-Latin or otherwise “exotic” script characters (e.g. Tamil diacritics).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '
    -2.70
     了
    -1.88
     créé
    -1.85
    a
    -1.78
    t
    -1.77
    菒
    -1.76
    of
    -1.74
     «
    -1.74
     &
    -1.70
    end
    -1.66
    POSITIVE LOGITS
    咘
    2.30
    replyreport
    2.02
    ⸂
    1.96
    ,’
    1.93
    ridescent
    1.91
    ឵
    1.91
    
    1.82
    
    1.81
    噲
    1.77
    (“
    1.77
    Activations Density 0.001%

    No Known Activations